Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.7206. Min Act: -0.1700
Data Index: 4704774 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6726. Min Act: -0.1700
Data Index: 1295734 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6726. Min Act: -0.1700
Data Index: 3794949 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6565. Min Act: -0.1700
Data Index: 3925644 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6565. Min Act: -0.1700
Data Index: 6604818 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6726. Min Act: -0.1700
Data Index: 8324729 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.6244. Min Act: -0.1700
Data Index: 336734 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5600. Min Act: -0.1700
Data Index: 5655198 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5923. Min Act: -0.1700
Data Index: 3576010 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5439. Min Act: -0.1700
Data Index: 6715686 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5600. Min Act: -0.1700
Data Index: 5401561 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5600. Min Act: -0.1700
Data Index: 5033583 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5600. Min Act: -0.1700
Data Index: 5371966 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5439. Min Act: -0.1700
Data Index: 1622803 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5277. Min Act: -0.1700
Data Index: 1045276 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5277. Min Act: -0.1700
Data Index: 2481366 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5439. Min Act: -0.1700
Data Index: 6162445 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5115. Min Act: -0.1700
Data Index: 955940 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5439. Min Act: -0.1700
Data Index: 3662607 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7206. Min Range: -2.7206
Max Act: 2.5277. Min Act: -0.1700
Data Index: 1340350 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19